© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-TRANSCODER-262K
    4. 218328
    Prev
    Next
    INDEX
    Explanations

    boys and girls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    älter
    0.29
    áver
    0.29
    getAsDouble
    0.28
     Ávila
    0.28
    𒉈
    0.28
    जफ्
    0.27
    httpRequest
    0.26
     AFC
    0.26
     complic
    0.26
     Moritz
    0.26
    POSITIVE LOGITS
    集合
    0.32
    Equ
    0.30
    HD
    0.30
    Deck
    0.30
    cion
    0.29
    說
    0.28
    係
    0.28
    PAR
    0.27
    ipart
    0.27
    ЕС
    0.26
    Activations Density 0.002%

    No Known Activations